© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28939
    Prev
    Next
    INDEX
    Explanations

    instances of the word "diss."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.14
    0.8%
    111
    +0.13
    0.7%
    468
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.14
    0.02
    203
    +0.13
    0.02
    467
    +0.11
    0.02
    Negative Logits
    anus
    -1.59
     Superior
    -1.38
    eer
    -1.36
     whole
    -1.36
    icia
    -1.34
    tis
    -1.30
     oral
    -1.29
    Inflater
    -1.28
    WARE
    -1.27
     {@
    -1.26
    POSITIVE LOGITS
    atisfaction
    2.05
    atisfied
    2.04
    olving
    1.92
    heets
    1.75
    ociation
    1.73
    olution
    1.72
    atisf
    1.71
    olutions
    1.70
    olute
    1.70
    olves
    1.69
    Activations Density 3.676%

    No Known Activations